Adaptive policies for time-varying stochastic systems under discounted criterion.
Nadine HilgertJ. Adolfo Minjárez-SosaPublished in: Math. Methods Oper. Res. (2001)
Keyphrases
- stochastic systems
- optimal policy
- predictive state representations
- sample path
- stochastic models
- conservation laws
- confidence intervals
- average cost
- markov decision processes
- markov decision process
- average reward
- asymptotic analysis
- long run
- infinite horizon
- feature selection
- finite horizon
- lost sales
- sample size
- state space
- probabilistic model
- dynamic programming